Map area integration method, device, storage medium and electronic device
By acquiring the set of maps and boundary coordinate points, and using neural networks to identify feature areas in the tile image, the problems of inefficient and inaccurate integration of map areas in the prior art are solved, and fast and accurate plot integration is achieved.
Patent Information
- Application Number
- CN201911233063.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2019-12-05
- Publication Date
- 2024-11-19
- Estimated Expiration
- 2039-12-05
AI Technical Summary
In the prior art, the integration efficiency of map areas is inefficient and inaccurate, and mainly relies on manual labor and labeling, resulting in a large amount of manpower and material resources and easy to cause errors.
By obtaining the set of maps and boundary coordinate points, the tile image set is determined, and the neural network is used to identify areas that meet preset features, and merge them into an integrated area set to achieve fast and accurate plot integration.
The rapid and accurate integration of map areas is achieved, which avoids the inefficiency and inaccuracy of manual integration, and improves the integration efficiency and accuracy.
Smart Images

Figure CN111753031B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of map surveying and mapping, and in particular, to a method, device, storage medium and electronic device for integrating map areas. Background Art
[0002] With the development of science and technology and the progress of society, the degree of automation in various industries is getting higher and higher. Traditional manual labor is gradually being replaced by automated equipment, thereby improving the productivity of the entire society.
[0003] In the field of map surveying and mapping, the existing division and integration of plots of land that meet preset characteristics in a designated area of a map (e.g., tea roads in a tea garden area, orchards in an orchard area, etc.) (i.e., plot integration) is still achieved manually. For example, plot integration is achieved through two methods: manual dotting and manual marking. Manual dotting refers to running along the boundaries of plots with a handheld surveying pole to integrate plots, and manual marking refers to using map marking tools to mark plots online to integrate plots. However, integrating plots manually has the disadvantages of low integration efficiency and inaccuracy. Summary of the invention
[0004] The purpose of the present application includes, for example, providing a method, device, storage medium and electronic device for integrating map areas, which can efficiently and accurately integrate plots of land.
[0005] The embodiments of the present application can be implemented as follows:
[0006] In a first aspect, an embodiment provides a method for integrating map areas, the method comprising: acquiring a map and a set of boundary coordinate points; the set of boundary coordinate points enclosing a target area on the map; determining a set of tile images covering at least the target area on the map based on the set of boundary coordinate points; the set of tile images comprising at least one tile image; identifying areas in each tile image that meet preset features through a neural network, and merging all areas that meet the preset features into an integrated area set.
[0007] In an optional embodiment, the step of determining a set of tile images covering at least the target area on the map based on the boundary coordinate point set includes: converting the coordinate system of the boundary coordinate point set to a Mercator coordinate system to obtain a first set of coordinate points to be processed corresponding to the boundary coordinate point set; determining a set of tile images of a preset map level on the map based on the first set of coordinate points to be processed, and the tile image set covers at least the area surrounded by the first set of coordinate points to be processed.
[0008] In an optional embodiment, the step of determining a set of tile images covering at least the target area on the map based on the set of boundary coordinate points includes: obtaining a minimum enclosing rectangle corresponding to the set of boundary coordinate points; determining a set of tile images of a preset map level on the map based on the minimum enclosing rectangle, and the set of tile images at least covers the minimum enclosing rectangle.
[0009] In an optional embodiment, the step of identifying areas in each tile image that meet preset characteristics through a neural network and merging all areas that meet the preset characteristics into an integrated area set includes: inputting each tile image into a trained neural network, and obtaining a set of pixel coordinate points corresponding to each tile image output by the neural network; the area surrounded by the set of pixel coordinate points represents the area that meets the preset characteristics; and determining the integrated area set based on the set of pixel coordinate points corresponding to all tile images.
[0010] In an optional embodiment, the step of determining an integrated area set based on a set of pixel coordinate points corresponding to all tile images includes: converting the coordinate system of the set of pixel coordinate points corresponding to all tile images into a longitude and latitude coordinate system to obtain a second set of coordinate points to be processed corresponding to the set of pixel coordinate points corresponding to all tile images; determining a deduplicated coordinate point set based on the second set of coordinate points to be processed; the difference between the longitude and latitude of two adjacent coordinate points of any coordinate point in the deduplicated coordinate point set is greater than or equal to a preset value; and determining an integrated area set based on the deduplicated coordinate point set.
[0011] In an optional embodiment, the step of determining an integrated area set based on the deduplicated coordinate point set includes: determining a smooth coordinate point set based on the deduplicated coordinate point set; an angle formed by any coordinate point in the smooth coordinate point set and its two adjacent coordinate points is less than a preset angle value; and determining an integrated area set based on the smooth coordinate point set.
[0012] In an optional embodiment, the step of determining an integrated area set based on the deduplicated coordinate point set includes: determining a smooth coordinate point set based on the deduplicated coordinate point set; the distance between any coordinate point in the smooth coordinate point set and a target line segment is greater than a preset distance, and the target line segment is a line segment formed by two coordinate points adjacent to any coordinate point; determining an integrated area set based on the smooth coordinate point set.
[0013] In a second aspect, an embodiment provides a device for integrating a map area, comprising: an acquisition module, used to acquire a map and a set of boundary coordinate points; the boundary coordinate point set encloses a target area on the map; an integration module, used to determine a set of tile images on the map that at least covers the target area based on the boundary coordinate point set; the tile image set includes at least one tile image; the integration module is also used to identify areas in each tile image that meet preset characteristics through a neural network, and merge all areas that meet the preset characteristics into an integrated area set.
[0014] In an optional embodiment, the integration module is used to convert the coordinate system of the boundary coordinate point set into a Mercator coordinate system to obtain a first set of coordinate points to be processed corresponding to the boundary coordinate point set; and to determine a tile image set of a preset map level on the map based on the first set of coordinate points to be processed, and the tile image set covers at least the area surrounded by the first set of coordinate points to be processed.
[0015] In an optional embodiment, the integration module is used to obtain the minimum enclosing rectangle corresponding to the set of boundary coordinate points; and to determine a set of tile images of a preset map level on the map based on the minimum enclosing rectangle, and the tile image set at least covers the minimum enclosing rectangle.
[0016] In an optional embodiment, the integration module is used to input each tile image into a trained neural network, and obtain a set of pixel coordinate points corresponding to each tile image output by the neural network; the area enclosed by the set of pixel coordinate points represents an area that meets preset characteristics; and is used to determine an integrated area set based on the pixel coordinate point sets corresponding to all tile images.
[0017] In an optional embodiment, the integration module is used to convert the coordinate system of the pixel coordinate point set corresponding to all tile images into a latitude and longitude coordinate system to obtain a second set of coordinate points to be processed corresponding to the pixel coordinate point set corresponding to all tile images; and to determine a deduplicated coordinate point set based on the second set of coordinate points to be processed; the difference between the longitude and latitude of two adjacent coordinate points of any coordinate point in the deduplicated coordinate point set is greater than or equal to a preset value; and to determine an integration area set based on the deduplicated coordinate point set.
[0018] In an optional embodiment, the integration module is used to determine a smooth coordinate point set based on the deduplicated coordinate point set; the angle formed by any coordinate point in the smooth coordinate point set and its two adjacent coordinate points is less than a preset angle value; and is used to determine an integrated area set based on the smooth coordinate point set.
[0019] In an optional embodiment, the integration module is used to determine a smooth coordinate point set based on the deduplicated coordinate point set; the distance between any coordinate point in the smooth coordinate point set and a target line segment is greater than a preset distance, and the target line segment is a line segment formed by two coordinate points adjacent to any one of the coordinate points; and is used to determine an integration area set based on the smooth coordinate point set.
[0020] In a third aspect, an embodiment provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the above-mentioned map area integration method when executed by a processor.
[0021] In a fourth aspect, an embodiment provides an electronic device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the memory via the bus, and the processor executes the machine-readable instructions to perform the above-mentioned map area integration method.
[0022] The beneficial effects of the embodiments of the present application include, for example: since the neural network has the advantages of being fast and accurate in identifying areas in an image that meet preset features, when integrating plots of land, the embodiments of the present application use a neural network to identify areas in each tile image that meet preset features, and merge all areas that meet the preset features into an integrated area set, thereby enabling the target areas on the map to be quickly and accurately identified and integrated, thereby avoiding the shortcomings of low integration efficiency and inaccuracy that exist when integrating plots manually. Therefore, the embodiments of the present application can efficiently and accurately integrate plots of land. BRIEF DESCRIPTION OF THE DRAWINGS
[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.
[0024] Figure 1 A structural block diagram of an electronic device provided in an embodiment of the present application;
[0025] Figure 2 A flow chart of a method for integrating map areas provided in an embodiment of the present application;
[0026] Figure 3 This is a schematic diagram of Map A of a grain planting base;
[0027] Figure 4 for Figure 3 A schematic diagram of a tile image map corresponding to the map A shown;
[0028] Figure 5 for Figure 3 The diagram shown is a schematic diagram of a set of tile images corresponding to the map A at the first map level;
[0029] Figure 6 for Figure 3 The shown map A is a schematic diagram of the integrated area after the map area is integrated;
[0030] Figure 7 Another flow chart of the method for integrating map areas provided in an embodiment of the present application;
[0031] Figure 8 Another flow chart of the method for integrating map areas provided in an embodiment of the present application;
[0032] Fig. 9 for Figure 5 A schematic diagram of the minimum circumscribed rectangle corresponding to the first set of coordinate points to be processed on map A shown;
[0033] Fig.10 Another flow chart of the method for integrating map areas provided in an embodiment of the present application;
[0034] Fig.11 for Figure 3 A schematic diagram of pixel coordinates of a tile image of map A output after being recognized by a neural network;
[0035] Fig.12 for Fig.10 A schematic diagram of a set of integrated regions corresponding to pixel coordinate points shown;
[0036] Fig.13 Another flow chart of the method for integrating map areas provided in an embodiment of the present application;
[0037] Fig.14 A schematic diagram of smoothing the area surrounded by a set of deduplicated coordinate points;
[0038] Fig.15 Another schematic diagram for smoothing the area surrounded by the set of deduplicated coordinate points;
[0039] Fig.16 A functional module diagram of a map area integration device provided in an embodiment of the present application.
[0040] Icons: 100 - electronic device; 110 - memory; 120 - processor; 130 - bus; 140 - communication interface; 200 - map area integration device; 210 - acquisition module; 220 - integration module. DETAILED DESCRIPTION
[0041] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations.
[0042] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for which protection is sought, but merely represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.
[0043] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.
[0044] In addition, the terms “first”, “second”, etc., if used, are merely used to distinguish between the descriptions and should not be understood as indicating or implying relative importance.
[0045] It should be noted that, in the absence of conflict, the features in the embodiments of the present application may be combined with each other.
[0046] In the process of implementing the technical solution of the embodiment of the present application, the inventor of the present application found that:
[0047] The existing division and integration of plots of land that meet preset characteristics in a designated area of a map (for example, tea roads in a tea garden area, orchards in an orchard area, etc.) (i.e., plot integration, marking out all plots that meet preset characteristics in a designated area) is still done manually. For example, plot integration is achieved through two methods: manual dotting and manual labeling. Manual dotting refers to running along the boundaries of plots with a handheld surveying pole to integrate the plots, and manual labeling refers to using map labeling tools to label plots online to integrate the plots. In the process of manually implementing plot integration, not only a large amount of manpower and material resources are required, but also dotting or labeling errors often occur, and a large amount of time is required to complete the integration of plots in an area.
[0048] Therefore, the existing manual integration of plots has the disadvantages of low integration efficiency and inaccuracy.
[0049] In order to improve the above defects, the embodiments of the present application propose a method, device, storage medium and electronic device for integrating map areas, which can efficiently and accurately integrate plots. It should be noted that the defects existing in the solutions in the above prior art are the results obtained by the inventor after practice and careful research. Therefore, the discovery process of the above problems and the solutions proposed by the embodiments of the present application for the above problems below should be the contributions made by the inventor to the present application during the application process.
[0050] Please refer to Figure 1 , which is a structural block diagram of an electronic device 100 provided in an embodiment of the present application. The electronic device 100 may include a memory 110, a processor 120, a bus 130 and a communication interface 140, and the memory 110, the processor 120 and the communication interface 140 are electrically connected to each other directly or indirectly to realize data transmission or interaction. For example, these elements can be electrically connected to each other through one or more buses 130 or signal lines. The processor 120 can process information and / or data related to the integration of map areas to perform one or more functions described in the present application. For example, the processor 120 can obtain a map and a set of boundary coordinate points through a network, and integrate the map area according to the above data, thereby realizing the map area integration method provided in the present application.
[0051] The memory 110 can be, but is not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable read-only memory (EEPROM), etc.
[0052] The processor 120 may be an integrated circuit chip with signal processing capability. The processor 120 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.
[0053] Understandably, Figure 1 The structure shown is for illustration only. The electronic device 100 may also include Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown. Figure 1 The components shown in the figure can be implemented by hardware, software or a combination thereof. In practical applications, the electronic device 100 can be a server, a mobile phone, a tablet computer, a notebook computer, an ultra-mobile personal computer (UMPC), a handheld computer, a netbook, a personal digital assistant (PDA), a wearable electronic device, a virtual reality device, and other electronic devices, so the embodiment of the present application does not limit the electronic device 100.
[0054] For ease of understanding, the following examples of this application will be Figure 1 Taking the electronic device 100 shown as an example, the map area integration method provided in the embodiment of the present application is specifically described in combination with the accompanying drawings.
[0055] Please refer to Figure 2 , Figure 2 A flowchart of a method for integrating map regions provided in an embodiment of the present application is shown. The method for integrating map regions can be applied to the electronic device 100 described above, and the method for integrating map regions may include the following steps:
[0056] S100, obtaining a map and a set of boundary coordinate points; the set of boundary coordinate points surrounds a target area on the map.
[0057] In some possible embodiments, Figure 3Taking the map A of the grain planting base shown in FIG. 1 as an example, when it is necessary to integrate a certain area on the map A of the grain planting base, the corresponding target area (i.e. Figure 3 The electronic device 100 can obtain the grain planting base map A and a set of boundary coordinate points on the boundary of the target area (i.e., area S), and it can be understood that the set of boundary coordinate points represents a target area enclosed on the map.
[0058] It should be noted that the above-mentioned map and boundary coordinate point set may be map and boundary coordinate point set data pre-stored in the storage medium of the electronic device, or map and boundary coordinate point set data obtained by the electronic device in real time from other terminals (for example, servers, cloud platforms, mobile terminals, etc.). Therefore, the embodiment of the present application does not limit the method for obtaining the map and boundary coordinate point set.
[0059] For example, in one possible application, the map may be pre-stored in a storage medium of an electronic device, and the boundary coordinate point set may be obtained by the electronic device in real time from a mobile terminal, that is, the user may operate the mobile terminal to send the boundary coordinate point set to the electronic device, and then the electronic device may obtain the map and the boundary coordinate point set. The mobile terminal may be pre-set with a corresponding plot integration program, and when the plot integration program is running, the mobile terminal may display the map through a display screen, and when the user circles a target area on the map on the display screen, the mobile terminal may generate a corresponding boundary coordinate point set (that is, the boundary coordinate point set surrounds a target area on the map), and send the boundary coordinate point set to the electronic device.
[0060] S110, determining a tile image set covering at least a target area on a map according to a set of boundary coordinate points; the tile image set includes at least one tile image.
[0061] Please refer to Figure 4 ,for Figure 3 The schematic diagram of the tile image map corresponding to the map A shown in FIG. 1 is a schematic diagram of the tile image map corresponding to the map A. An existing map usually corresponds to multiple levels of tile image maps according to the map level (also indicating the zoom level of the map), such as Figure 4 In the map A, the map A corresponds to 4 tile images at the first map level, namely tile images 1-4. Correspondingly, for tile image 1, it can also correspond to several tile images at the second map level. And so on, map A corresponds to multiple tile images at different map levels.
[0062] In some possible embodiments, Figure 5 (for Figure 3Taking the map A shown in FIG. 1 as an example, the target area is the area S surrounded by solid lines. After acquiring the map A and the boundary coordinate point set, the electronic device 100 can determine a tile image set that at least covers the area S on the map A according to the coordinates of the boundary coordinate point set. Since the tile images 1-4 just cover the area S, the determined tile image set includes at least the tile images 1-4.
[0063] For ease of understanding, this article only Figure 4 The map area integration method provided in the present application is explained on the basis of, in fact, the map area integration method provided in the present application can integrate the map area based on multiple tile images at a specified map level, or can integrate the map area based on multiple tile images at multiple map levels, and the present application does not limit this.
[0064] S120, identifying regions in each tile image that meet preset features through a neural network, and merging all regions that meet the preset features into an integrated region set.
[0065] In some possible embodiments, a trained neural network may be pre-stored in the storage medium of the electronic device 100. After training, the neural network can be used to efficiently and accurately identify areas that meet preset characteristics. For example, when the neural network is used to identify a tea road in a tea garden area and a fruit forest in an orchard area in an image, an image can be input into the neural network, and then the neural network outputs the image with the tea road and fruit forest areas marked.
[0066] Furthermore, after determining a set of tile images that at least cover the target area, the electronic device 100 can input each tile image as input data to the neural network, and the neural network will identify each image to identify areas in each image that meet preset characteristics (for example, the tea ceremony area in the tea garden area, the fruit forest area in the orchard area, etc.). After identifying areas that meet the preset characteristics in all tile images, all areas that meet the preset characteristics can be merged into an integrated area set to achieve the purpose of plot integration.
[0067] Continue with Figure 5 Taking the application scenario shown as an example, assuming that the neural network is used to identify the area in each image that meets the characteristics of grains (for example, wheat, rice, corn, etc.), the electronic device 100 can input the tile images 1-4 into the pre-trained neural network respectively after determining that the tile image set includes at least tile images 1-4, and then obtain the output data corresponding to each tile image, which can represent the area that meets the preset characteristics, and finally merge all the output data into an integrated area set to achieve the integration of the grain plots, such as Figure 6(for Figure 3 The map A shown in the integrated area schematic diagram after the map area is integrated is shown, that is, all grain plots in the target area are marked out.
[0068] It should be understood that since neural networks can be used to efficiently and accurately identify areas that meet preset characteristics, they have the advantage of quickly and accurately identifying areas in images that meet preset characteristics. When integrating plots of land, the embodiments of the present application use neural networks to identify areas that meet preset characteristics in each tile image, and merge all areas that meet the preset characteristics into an integrated area set. This allows the target areas on the map to be quickly and accurately identified and integrated, avoiding the shortcomings of low integration efficiency and inaccuracy that exist when integrating plots manually. Therefore, the embodiments of the present application can efficiently and accurately integrate plots of land.
[0069] Further, in Figure 1 Based on this, a possible implementation of a complete solution is given below. For details, please refer to Figure 7 , Figure 7 Another flowchart of the method for integrating map areas provided in the embodiment of the present application is shown. It should be noted that the method for integrating map areas provided in the embodiment of the present application is not based on Figure 7 The specific order below is not limited. It should be understood that in other embodiments, the order of some steps in the map area integration method provided in the embodiment of the present application can be interchanged according to actual needs, or some steps can be omitted or deleted. Figure 7 The specific process shown is described in detail.
[0070] Regarding how to determine a tile image set that at least covers the target area on the map according to the boundary coordinate point set, S110 may include:
[0071] S110A: Convert the coordinate system of the boundary coordinate point set to the Mercator coordinate system to obtain a first coordinate point set to be processed corresponding to the boundary coordinate point set.
[0072] In some possible embodiments, when the coordinate system of the boundary coordinate point set is not the Mercator coordinate system, the coordinate system of the boundary coordinate point set is converted to the Mercator coordinate system to obtain the corresponding first coordinate point set to be processed. It can be understood that in S110A, when the coordinate system of the boundary coordinate point set is already the Mercator coordinate system, the boundary coordinate point set can be directly used as the first coordinate point set to be processed.
[0073] S110B: Determine a tile image set of a preset map level on the map according to the first set of coordinate points to be processed, and the tile image set at least covers an area surrounded by the first set of coordinate points to be processed.
[0074] In some possible embodiments, after obtaining the first set of coordinate points to be processed corresponding to the boundary coordinate point set, continue with Figure 5 Taking the map shown as an example, assuming that the area surrounded by the first set of coordinate points to be processed is area S, and the preset map level is the first map level, a tile image set in the first map level that covers at least area S can be determined on map A according to the coordinates of each coordinate point in the first set of coordinate points to be processed. In other words, a tile image set of the first map level can be determined on map A according to the coordinates of each coordinate point in the first set of coordinate points to be processed, and the tile image set covers at least area S, so the determined tile image set includes at least tile images 1-4.
[0075] Among them, according to the Mercator projection principle, the maximum and minimum row and column numbers of the longitude and latitude grid covered by the first set of coordinate points to be processed in the first map level can be calculated, and then a tile image set can be determined according to the maximum and minimum row and column numbers and the first map level, and the tile image set at least covers the area surrounded by the first set of coordinate points to be processed.
[0076] It should be understood that since a set of tile images covering at least the area enclosed by the first set of coordinate points to be processed is determined on the map only at one preset map level, the present application can avoid the problem of large amount of processing data when determining tile image sets at multiple map levels.
[0077] In practical applications, the preset map level may be level 12. After many experiments, the inventors found that the clarity of the tile image at the level 12 map not only enables the neural network to accurately identify areas that meet the preset features, but also avoids the tile image clarity being too high, resulting in the neural network processing time being too long. That is, setting the preset map level to level 12 can improve the processing efficiency and accuracy of the neural network.
[0078] Regarding how to determine a set of tile images of a preset map level covering at least the area surrounded by the first set of coordinate points to be processed on the map according to the first set of coordinate points to be processed, Figure 7 Based on Figure 8 , S110B may include:
[0079] S110B-1, obtaining the minimum circumscribed rectangle corresponding to the first set of coordinate points to be processed.
[0080] In some possible embodiments, please refer to Fig. 9 , the area S surrounded by the solid lines is the area surrounded by the first set of coordinate points to be processed, and the minimum circumscribed rectangle corresponding to the area S is the area G surrounded by the solid lines in the figure.
[0081] S110B-2, determining a tile image set of a preset map level on the map according to the minimum bounding rectangle, and the tile image set at least covers the minimum bounding rectangle.
[0082] Please continue to refer to Fig. 9 After obtaining the minimum circumscribed rectangle (i.e., area G), a set of tile images of a preset map level that at least covers area G can be determined on the map based on area G. Since tile images 1-4 can at least cover area G, the determined tile image set includes at least tile images 1-4.
[0083] It should be understood that since the tile image set of the preset map level is obtained by obtaining the minimum circumscribed rectangle corresponding to the first set of coordinate points to be processed, the method of obtaining the tile image set is simplified, thereby improving the processing efficiency of the integrated plots.
[0084] It should also be added that, in order to accurately obtain data corresponding to the input tile image from the data output by the neural network, before identifying the area that meets the preset characteristics in each tile image through the neural network and merging all the areas that meet the preset characteristics into an integrated area set, the method provided by the present application may also include:
[0085] A designated ID and a corresponding task name are generated for the above tile image set. The task name may include at least one of year, month, day, underscore, and a specific random number.
[0086] In another possible embodiment, how to determine a tile image set that at least covers a target area on a map according to a set of boundary coordinate points, Figure 7 Based on Fig.10 , S110 may include:
[0087] S110a, obtaining the minimum circumscribed rectangle corresponding to the boundary coordinate point set.
[0088] In some possible embodiments, please refer to Fig. 9 , the area S surrounded by the solid lines is the area surrounded by the set of boundary coordinate points, and the minimum circumscribed rectangle corresponding to the area S is the area G surrounded by the solid lines in the figure.
[0089] S110b: Determine a set of tile images of a preset map level on the map according to the minimum bounding rectangle, and the set of tile images at least covers the minimum bounding rectangle.
[0090] Please continue to refer to Fig. 9Assuming that the preset map level is the first map level, after obtaining the minimum enclosing rectangle (i.e., area G), a set of tile images of the preset map level that at least covers area G can be determined on the map based on area G. Since the map level of tile images 1-4 is the first map level and can at least cover area G, the determined tile image set includes at least tile images 1-4.
[0091] It should be understood that since the tile image set of the preset map level is obtained by obtaining the minimum circumscribed rectangle corresponding to the boundary coordinate point set, the method of obtaining the tile image set is simplified, thereby improving the processing efficiency of the integrated plot.
[0092] Please refer to Figure 7 Regarding how to identify the region that meets the preset features in each tile image through a neural network and merge all the regions that meet the preset features into an integrated region set, S120 may include:
[0093] S120A, input each tile image into the trained neural network, and obtain a set of pixel coordinate points corresponding to each tile image output by the neural network; the area surrounded by the set of pixel coordinate points represents an area that meets preset characteristics.
[0094] In some possible embodiments, in order to adapt to the needs of module development and flexibly process data, the trained neural network can be used only to output only the corresponding set of pixel coordinate points when identifying areas in the tile image that meet preset characteristics, and the area surrounded by the set of pixel coordinate points represents the area that meets the preset characteristics.
[0095] After inputting each tile image into the trained neural network, the electronic device 100 can obtain a set of pixel coordinate points corresponding to each tile image output by the neural network, such as Fig.11 (for Figure 3 The schematic diagram of the pixel coordinates of the tile image of map A output after the neural network recognition shows all the points in the tile images 1-4. At this time, the area surrounded by the set of pixel coordinates represents the area that meets the preset characteristics.
[0096] It can be understood that when the pixel coordinate point set corresponding to each tile image is obtained, for two pixel coordinate point sets corresponding to adjacent tile images, there may be pixel coordinate points with overlapping coordinates. For example, in the two pixel coordinate point sets corresponding to tile image 1 and tile image 2, there may be pixel coordinate points with the same coordinates on the common edge of tile image 1 and tile image 2.
[0097] It should also be added that, in practical applications, due to the limited storage medium space of the electronic device 100, when the amount of pixel coordinate point set data corresponding to each tile image output by the neural network is too large, it may not be stored. When obtaining the pixel coordinate point set corresponding to each tile image output by the neural network, the step may include:
[0098] Acquire processing result data fed back by the neural network, wherein the processing result data includes an identification field;
[0099] When the identification field is true, a set of pixel coordinate points corresponding to each tile image is obtained from the storage space pointed to by the storage coordinate field of the processing result data;
[0100] When the identification field is false, a set of pixel coordinate points corresponding to each tile image is obtained from the storage medium of the device running the neural network. The neural network can be run on the electronic device 100 provided in the present application, or on other devices that communicate with the electronic device 100, and the present application does not limit this.
[0101] It should be understood that when the amount of pixel coordinate point set data corresponding to each tile image output by the neural network is too large, the device running the neural network can store the data in other storage spaces and set the feedback identification field to true, thereby ensuring that the electronic device 100 can correctly obtain the pixel coordinate point set corresponding to each tile image output by the neural network.
[0102] S120B: Determine an integration region set according to a pixel coordinate point set corresponding to all tile images.
[0103] In some possible embodiments, continue with Fig.11 For example, all pixel coordinate points with the same coordinates can be merged, and the pixel coordinate point sets corresponding to all tile images can also be merged, and the connected areas in the areas surrounded by all pixel coordinate point sets can be merged to obtain Fig.12 (for Fig.11 Schematic diagram of the integrated area set corresponding to the pixel coordinate points shown) to restore the actual land parcel integration situation.
[0104] In practical applications, all tile images can be combined into a large image first, and then the image is input into the trained neural network to identify all areas in the image that meet the preset features, and finally all areas that meet the preset features are merged into an integrated area set.
[0105] How to determine the integration area set based on the pixel coordinate point set corresponding to all tile images? Figure 7 Based on Fig.13, S120B may include:
[0106] S120B-1, converting the coordinate system of the pixel coordinate point set corresponding to all tile images into a longitude and latitude coordinate system, and obtaining a second coordinate point set to be processed corresponding to the pixel coordinate point set corresponding to all tile images.
[0107] Since the coordinate system of the pixel coordinate points is the pixel coordinate system, it is difficult to perform spatial algorithm analysis on the pixel coordinate system. In order to simplify the algorithm and improve the analysis efficiency, the coordinate system of the pixel coordinate point set corresponding to all tile images can be converted to the longitude and latitude coordinate system to obtain a second set of coordinate points to be processed corresponding to the pixel coordinate point set corresponding to all tile images (the second set of coordinate points to be processed includes all the pixel coordinate points in the pixel coordinate point set).
[0108] S120B-2, determining a deduplicated coordinate point set according to the second coordinate point set to be processed; the difference between the longitude and latitude of two adjacent coordinate points of any coordinate point in the deduplicated coordinate point set is greater than or equal to a preset value.
[0109] In some possible embodiments, since the obtained second set of coordinate points to be processed is very dense, in order to improve the analysis efficiency, the second set of coordinate points to be processed may be deduplicated. For example, each coordinate point in the second set of coordinate points to be processed may be traversed, and coordinate points that satisfy the condition that the difference between the longitude and latitude of two adjacent coordinate points is less than a preset value (the preset value may be 0.000000001) may be removed until the difference between the longitude and latitude of two adjacent coordinate points of any coordinate point in the second set of coordinate points to be processed is greater than or equal to the preset value.
[0110] S120B-3, determine an integrated area set based on the deduplicated coordinate point set.
[0111] In some possible embodiments, the obtained set of deduplicated coordinate points may enclose at least one area, and all the enclosed areas may be determined as an integrated area set, thereby achieving land parcel integration.
[0112] In order to smooth the area surrounded by the deduplicated coordinate point set, in a possible embodiment, S120B-3 may include: determining a smoothed coordinate point set according to the deduplicated coordinate point set; the angle formed by any coordinate point in the smoothed coordinate point set and its two adjacent coordinate points is less than a preset angle value; and determining an integrated area set according to the smoothed coordinate point set.
[0113] Assuming the preset angle value is 90°, please refer to Fig.14, the angle formed by the coordinate point A and its two adjacent coordinate points B and C is α, and when α is greater than or equal to 90°, the coordinate point A is removed. Then, each coordinate point in the deduplicated coordinate point set can be traversed, and the coordinate points that satisfy the angle formed by the two adjacent coordinate points is greater than or equal to the preset angle value are removed, until the angle formed by any coordinate point in the deduplicated coordinate point set and its two adjacent coordinate points is less than the preset angle value. Then, the integrated area set is determined according to the smoothed coordinate point set. This step can refer to S120B-3 and will not be repeated here.
[0114] It should be understood that by removing the coordinate points whose included angle formed by the two adjacent coordinate points is greater than or equal to the preset angle value, the area enclosed by the deduplicated coordinate point set becomes smoother, and the number of coordinate points in the deduplicated coordinate point set is reduced, thereby improving the efficiency and accuracy of the integrated plots.
[0115] In another possible embodiment, regarding how to determine the integration area set according to the deduplicated coordinate point set, S120B-3 may include: determining a smooth coordinate point set according to the deduplicated coordinate point set; the distance between any coordinate point in the smooth coordinate point set and the target line segment is greater than a preset distance, and the target line segment is a line segment formed by two coordinate points adjacent to any coordinate point. And determining the integration area set according to the smooth coordinate point set.
[0116] Assuming the distance is 1m, please refer to Fig.15 , the line segment formed by the two coordinate points B and C adjacent to the coordinate point A is BC, and the distance between A and BC is AD. When AD is less than or equal to 1m, the coordinate point A is removed. Then, each coordinate point in the deduplicated coordinate point set can be traversed, and the coordinate points that meet the distance between the target line segment and the preset distance can be removed, until the angle formed by any coordinate point in the deduplicated coordinate point set and its two adjacent coordinate points is less than the preset angle value. Then, the integrated area set is determined according to the smoothed coordinate point set. This step can refer to S120B-3 and will not be repeated here.
[0117] It should be understood that by removing coordinate points whose distance to the target line segment is less than or equal to the preset distance, the area enclosed by the deduplicated coordinate point set becomes smoother, and the number of coordinate points in the deduplicated coordinate point set is reduced, thereby improving the efficiency and accuracy of the integrated plots.
[0118] In order to execute the corresponding steps in the above embodiments and various possible methods, a method for implementing a map area integration device is given below. Fig.16 , Fig.16A functional module diagram of the map area integration device provided in the embodiment of the present application is shown. It should be noted that the basic principle and technical effect of the map area integration device 200 provided in this embodiment are the same as those of the above embodiment. For the sake of brief description, for the parts not mentioned in this embodiment, reference can be made to the corresponding contents in the above embodiment. The map area integration device 200 includes: an acquisition module 210 and an integration module 220.
[0119] Optionally, the above modules can be stored in the memory in the form of software or firmware or solidified in the operating system (OS) of the electronic device 100 provided in the present application, and can be executed by the processor in the electronic device 100. At the same time, the data, program codes, etc. required to execute the above modules can be stored in the memory.
[0120] The acquisition module 210 may be used to acquire a map and a set of boundary coordinate points; the set of boundary coordinate points surrounds a target area on the map.
[0121] It can be understood that the acquisition module 210 can be used to support the electronic device 100 to execute the above S100, etc., and / or other processes for the technology described in this document.
[0122] The integration module 220 can be used to determine a set of tile images that at least cover the target area on the map based on a set of boundary coordinate points; the tile image set includes at least one tile image; and is used to identify areas in each tile image that meet preset characteristics through a neural network, and merge all areas that meet the preset characteristics into an integrated area set.
[0123] It is understandable that the integration module 220 can be used to support the electronic device 100 to execute the above-mentioned S110, S120, etc., and / or other processes for the technology described herein.
[0124] The integration module 220 can be used to convert the coordinate system of the boundary coordinate point set into the Mercator coordinate system to obtain a first set of coordinate points to be processed corresponding to the boundary coordinate point set; and to determine a tile image set of a preset map level on the map based on the first set of coordinate points to be processed, and the tile image set at least covers the area surrounded by the first set of coordinate points to be processed.
[0125] It is understandable that the integration module 220 can be used to support the electronic device 100 to execute the above-mentioned S110A, S110B, etc., and / or other processes for the technology described herein.
[0126] Regarding how to determine a tile image set of a preset map level on a map that at least covers the area enclosed by the first set of coordinate points to be processed based on the first set of coordinate points to be processed, the integration module 220 can be used to obtain the minimum enclosing rectangle corresponding to the first set of coordinate points to be processed; and to determine a tile image set of a preset map level on a map based on the minimum enclosing rectangle, and the tile image set at least covers the minimum enclosing rectangle.
[0127] It is understandable that the integration module 220 can be used to support the electronic device 100 to execute the above-mentioned S110B-1, S110B-2, etc., and / or other processes for the technology described herein.
[0128] Regarding how to determine a set of tile images that at least covers a target area on a map based on a set of boundary coordinate points, the integration module 220 can be used to obtain a minimum enclosing rectangle corresponding to the set of boundary coordinate points; and to determine a set of tile images of a preset map level on a map based on the minimum enclosing rectangle, and the set of tile images at least covers the minimum enclosing rectangle.
[0129] It is understandable that the integration module 220 can be used to support the electronic device 100 to execute the above-mentioned S110a, S110b, etc., and / or other processes for the technology described herein.
[0130] As for how to identify the areas in each tile image that meet the preset characteristics through a neural network, and merge all the areas that meet the preset characteristics into an integrated area set, the integration module 220 can be used to input each tile image into a trained neural network, and obtain a set of pixel coordinate points corresponding to each tile image output by the neural network; the area surrounded by the set of pixel coordinate points represents the area that meets the preset characteristics; and is used to determine the integrated area set based on the set of pixel coordinate points corresponding to all tile images.
[0131] It is understandable that the integration module 220 can be used to support the electronic device 100 to execute the above-mentioned S120A, S120B, etc., and / or other processes for the technology described in this document.
[0132] As for how to determine the integration area set based on the pixel coordinate point set corresponding to all tile images, the integration module 220 can be used to convert the coordinate system of the pixel coordinate point set corresponding to all tile images into a longitude and latitude coordinate system to obtain a second set of coordinate points to be processed corresponding to the pixel coordinate point set corresponding to all tile images; and to determine a deduplicated coordinate point set based on the second set of coordinate points to be processed; the difference between the longitude and latitude of two adjacent coordinate points of any coordinate point in the deduplicated coordinate point set is greater than or equal to a preset value; and to determine the integration area set based on the deduplicated coordinate point set.
[0133] It can be understood that the integration module 220 can be used to support the electronic device 100 to execute the above-mentioned S120B-1, S120B-2, S120B-3, etc., and / or other processes for the technology described in this document.
[0134] Based on the above method embodiment, the embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above map area integration method are executed.
[0135] Specifically, the storage medium can be a general storage medium, such as a mobile disk, a hard disk, etc. When the computer program on the storage medium is run, it can execute the above-mentioned map area integration method, thereby solving the problems of low integration efficiency and inaccuracy in the existing land integration method, and achieving efficient and accurate integration of land plots.
[0136] In summary, the embodiments of the present application provide a method, device, storage medium and electronic device for integrating map areas, the method comprising: obtaining a map and a set of boundary coordinate points; the set of boundary coordinate points encloses a target area on the map; determining a set of tile images that at least cover the target area on the map according to the set of boundary coordinate points; the set of tile images includes at least one tile image; identifying the area that meets the preset characteristics in each tile image through a neural network, and merging all the areas that meet the preset characteristics into an integrated area set. Since the neural network has the advantages of being fast and accurate in identifying the area that meets the preset characteristics in the image, when integrating the plots, the embodiments of the present application use the neural network to identify the area that meets the preset characteristics in each tile image, and merge all the areas that meet the preset characteristics into an integrated area set, which can realize the rapid and accurate identification and integration of the target area on the map, avoiding the shortcomings of low integration efficiency and inaccuracy when integrating the plots manually, so the embodiments of the present application can integrate the plots efficiently and accurately.
[0137] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.
Claims
1. A method for integrating map areas, characterized in that: The method comprises: Acquire a map and a set of boundary coordinate points; the set of boundary coordinate points encloses a target area on the map; Determining a set of tile images covering at least the target area on the map according to the set of boundary coordinate points; the set of tile images includes at least one tile image; Identify the regions that meet the preset features in each tile image through a neural network, and merge all the regions that meet the preset features into an integrated region set; The steps of identifying the area meeting the preset characteristics in each tile image through a neural network and merging all the areas meeting the preset characteristics into an integrated area set include: Input each tile image into a trained neural network, and obtain a set of pixel coordinate points of an area meeting the preset characteristics corresponding to each tile image output by the neural network; the area surrounded by the set of pixel coordinate points represents the area meeting the preset characteristics; Determine the integration area set according to the pixel coordinate point set corresponding to all tile images; The step of determining a set of tile images covering at least the target area on the map according to the set of boundary coordinate points comprises: Obtain the minimum bounding rectangle corresponding to the boundary coordinate point set; A tile image set of a preset map level is determined on the map according to the minimum bounding rectangle, and the tile image set at least covers the minimum bounding rectangle.
2. The method according to claim 1, characterized in that The step of determining a set of tile images covering at least the target area on the map according to the set of boundary coordinate points comprises: Converting the coordinate system of the boundary coordinate point set to a Mercator coordinate system to obtain a first set of coordinate points to be processed corresponding to the boundary coordinate point set; A tile image set of a preset map level is determined on the map according to the first set of coordinate points to be processed, and the tile image set at least covers an area surrounded by the first set of coordinate points to be processed.
3. The method according to claim 1, characterized in that The steps of identifying the area meeting the preset characteristics in each tile image through a neural network and merging all the areas meeting the preset characteristics into an integrated area set include: Input each tile image into a trained neural network, and obtain a set of pixel coordinate points corresponding to each tile image output by the neural network; the area surrounded by the set of pixel coordinate points represents an area that meets the preset characteristics; The integration area set is determined according to the pixel coordinate point set corresponding to all tile images.
4. The method according to claim 3, characterized in that: The steps of determining the integration area set according to the pixel coordinate point set corresponding to all tile images include: Convert the coordinate system of the pixel coordinate point set corresponding to all tile images to the longitude and latitude coordinate system to obtain a second coordinate point set to be processed corresponding to the pixel coordinate point set corresponding to all tile images; Determine a deduplicated coordinate point set according to the second set of coordinate points to be processed; the difference between the longitude and latitude of two adjacent coordinate points of any coordinate point in the deduplicated coordinate point set is greater than or equal to a preset value; An integration area set is determined according to the deduplicated coordinate point set.
5. The method according to claim 4, characterized in that The step of determining the integrated area set according to the deduplicated coordinate point set comprises: Determine a smooth coordinate point set according to the deduplicated coordinate point set; the angle formed by any coordinate point in the smooth coordinate point set and its two adjacent coordinate points is less than a preset angle value; An integration area set is determined according to the smooth coordinate point set.
6. The method according to claim 4, characterized in that The step of determining the integrated area set according to the deduplicated coordinate point set comprises: Determine a smooth coordinate point set according to the deduplicated coordinate point set; the distance between any coordinate point in the smooth coordinate point set and a target line segment is greater than a preset distance, and the target line segment is a line segment formed by two coordinate points adjacent to the any coordinate point; An integration area set is determined according to the smooth coordinate point set.
7. A map area integration device, characterized in that: include: An acquisition module, used to acquire a map and a set of boundary coordinate points; the set of boundary coordinate points surrounds a target area on the map; An integration module, used to determine a set of tile images covering at least the target area on the map according to the set of boundary coordinate points; the set of tile images includes at least one tile image; The integration module is further used to identify the area that meets the preset characteristics in each tile image through a neural network, and merge all the areas that meet the preset characteristics into an integrated area set; The integration module is specifically used for: Each tile image is input into a trained neural network, and a set of pixel coordinate points of an area meeting the preset characteristics corresponding to each tile image output by the neural network is obtained; the area surrounded by the set of pixel coordinate points represents the area meeting the preset characteristics; Determine the integration area set according to the pixel coordinate point set corresponding to all tile images; The integration module is used to obtain the minimum bounding rectangle corresponding to the boundary coordinate point set; And it is used to determine a tile image set of a preset map level on the map according to the minimum bounding rectangle, and the tile image set at least covers the minimum bounding rectangle.
8. The device according to claim 7, characterized in that The integration module is used to convert the coordinate system of the boundary coordinate point set into a Mercator coordinate system to obtain a first coordinate point set to be processed corresponding to the boundary coordinate point set; And it is used to determine a tile image set of a preset map level on the map according to the first set of coordinate points to be processed, and the tile image set at least covers the area surrounded by the first set of coordinate points to be processed.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for integrating map areas according to any one of claims 1 to 6 is implemented.
10. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the memory via the bus, and the processor executes the machine-readable instructions to perform the map area integration method as described in any one of claims 1-6.
